{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T18:36:28Z","timestamp":1790879788436,"version":"4.1.0"},"publisher-location":"Cham","reference-count":64,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032370402","type":"print"},{"value":"9783032370419","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-3-032-37041-9_20","type":"book-chapter","created":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T07:30:15Z","timestamp":1788939015000},"page":"371-390","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Agentic Collaborative Cognition for\u00a0Zero-Shot 3D Understanding"],"prefix":"10.1007","author":[{"given":"Wenxin","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bo","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Feng","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zixuan","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wen","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Changsheng","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yinjie","family":"Lei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,10]]},"reference":[{"key":"20_CR1","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"422","DOI":"10.1007\/978-3-030-58452-8_25","volume-title":"Computer Vision \u2013 ECCV 2020","author":"P Achlioptas","year":"2020","unstructured":"Achlioptas, P., Abdelreheem, A., Xia, F., Elhoseiny, M., Guibas, L.: ReferIt3D: neural listeners for fine-grained 3D object identification in real-world scenes. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 422\u2013440. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_25"},{"key":"20_CR2","doi-asserted-by":"crossref","unstructured":"Alayrac, J.B., et al.: Flamingo: a visual language model for few-shot learning. In: Advances in neural information processing systems (NeurIPS), vol. 35, pp. 23716\u201323736 (2022)","DOI":"10.52202\/068431-1723"},{"issue":"2","key":"20_CR3","doi-asserted-by":"publisher","first-page":"28","DOI":"10.3390\/computers11020028","volume":"11","author":"F Arena","year":"2022","unstructured":"Arena, F., Collotta, M., Pau, G., Termine, F.: An overview of augmented reality. Computers 11(2), 28 (2022)","journal-title":"Computers"},{"key":"20_CR4","doi-asserted-by":"crossref","unstructured":"Azuma, D., Miyanishi, T., Kurita, S., Kawanabe, M.: ScanQA: 3D question answering for spatial scene understanding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 19129\u201319139 (2022)","DOI":"10.1109\/CVPR52688.2022.01854"},{"key":"20_CR5","unstructured":"Bai, J., et al.: Qwen-VL: a frontier large vision-language model with versatile abilities. arXiv preprint arXiv:2308.12966$$\\textbf{1}$$(2), 3 (2023)"},{"key":"20_CR6","unstructured":"Bai, S., et\u00a0al.: Qwen2.5-VL technical report. arXiv preprint arXiv:2502.13923 (2025)"},{"key":"20_CR7","doi-asserted-by":"crossref","unstructured":"Chang, C.P., Wang, S., Pagani, A., Stricker, D.: MiKASA: multi-key-anchor & scene-aware transformer for 3D visual grounding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 14131\u201314140 (2024)","DOI":"10.1109\/CVPR52733.2024.01340"},{"key":"20_CR8","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"202","DOI":"10.1007\/978-3-030-58565-5_13","volume-title":"Computer Vision \u2013 ECCV 2020","author":"DZ Chen","year":"2020","unstructured":"Chen, D.Z., Chang, A.X., Nie\u00dfner, M.: ScanRefer: 3D object localization in RGB-D scans using natural language. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12365, pp. 202\u2013221. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58565-5_13"},{"key":"20_CR9","doi-asserted-by":"crossref","unstructured":"Chen, Z., Gholami, A., Nie\u00dfner, M., Chang, A.X.: Scan2cap: context-aware dense captioning in RGB-D scans. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3193\u20133203 (2021)","DOI":"10.1109\/CVPR46437.2021.00321"},{"issue":"70","key":"20_CR10","first-page":"1","volume":"25","author":"HW Chung","year":"2024","unstructured":"Chung, H.W., et al.: Scaling instruction-finetuned language models. J. Mach. Learn. Res. (JMLR) 25(70), 1\u201353 (2024)","journal-title":"J. Mach. Learn. Res. (JMLR)"},{"key":"20_CR11","doi-asserted-by":"crossref","unstructured":"Dai, A., Chang, A.X., Savva, M., Halber, M., Funkhouser, T., Nie\u00dfner, M.: ScanNet: richly-annotated 3D reconstructions of indoor scenes. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5828\u20135839 (2017)","DOI":"10.1109\/CVPR.2017.261"},{"key":"20_CR12","doi-asserted-by":"crossref","unstructured":"Fan, Y., et al.: Embodied videoagent: persistent memory from egocentric videos and embodied sensors enables dynamic scene understanding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6342\u20136352 (2025)","DOI":"10.1109\/ICCV51701.2025.00598"},{"key":"20_CR13","doi-asserted-by":"crossref","unstructured":"Fu, R., Liu, J., Chen, X., Nie, Y., Xiong, W.: Scene-LLM: extending language model for 3D visual reasoning. In: 2025 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV), pp. 2195\u20132206. IEEE (2025)","DOI":"10.1109\/WACV61041.2025.00220"},{"key":"20_CR14","doi-asserted-by":"crossref","unstructured":"Gu, Q., et al.: Conceptgraphs: open-vocabulary 3D scene graphs for perception and planning. In: 2024 IEEE International Conference on Robotics and Automation (ICRA), pp. 5021\u20135028. IEEE (2024)","DOI":"10.1109\/ICRA57147.2024.10610243"},{"key":"20_CR15","doi-asserted-by":"crossref","unstructured":"Hong, Y., et al.: 3D-LLM: injecting the 3d world into large language models. In: Advances in Neural Information Processing Systems (NeurIPS), vol. 36, pp. 20482\u201320494 (2023)","DOI":"10.52202\/075280-0900"},{"key":"20_CR16","doi-asserted-by":"crossref","unstructured":"Huang, H., et al.: Chat-scene: bridging 3D scene and large language models with object identifiers. In: Advances in Neural Information Processing Systems (NeurIPS), vol. 37, pp. 113991\u2013114017 (2024)","DOI":"10.52202\/079017-3620"},{"key":"20_CR17","unstructured":"Huang, J., et al.: An embodied generalist agent in 3D world. In: Proceedings of the International Conference on Machine Learning (ICML) (2024)"},{"key":"20_CR18","doi-asserted-by":"crossref","unstructured":"Huang, X., Wu, J., Xie, Q., Han, K.: MLLMs need 3D-aware representation supervision for scene understanding. arXiv preprint arXiv:2506.01946 (2025)","DOI":"10.52202\/085713-2282"},{"key":"20_CR19","unstructured":"Hurst, A., et al.: GPT-4o system card. arXiv preprint arXiv:2410.21276 (2024)"},{"key":"20_CR20","doi-asserted-by":"publisher","unstructured":"Jain, A., Gkanatsios, N., Mediratta, I., Fragkiadaki, K.: Bottom up top down detection transformers for language grounding in images and point clouds. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13696, pp. 417\u2013433. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20059-5_24","DOI":"10.1007\/978-3-031-20059-5_24"},{"key":"20_CR21","doi-asserted-by":"crossref","unstructured":"Jin, Z., Hayat, M., Yang, Y., Guo, Y., Lei, Y.: Context-aware alignment and mutual masking for 3D-language pre-training. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 10984\u201310994 (2023)","DOI":"10.1109\/CVPR52729.2023.01057"},{"key":"20_CR22","doi-asserted-by":"crossref","unstructured":"Jin, Z., et al.: SPAZER: spatial-Semantic progressive reasoning agent for zero-shot 3D visual grounding. arXiv preprint arXiv:2506.21924 (2025)","DOI":"10.52202\/085713-5518"},{"key":"20_CR23","unstructured":"Ke, F., et al.: VIEW2SPACE: studying multi-view visual reasoning from sparse observations. arXiv preprint arXiv:2603.16506 (2026)"},{"key":"20_CR24","unstructured":"Li, J., Li, D., Savarese, S., Hoi, S.: Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models. In: Proceedings of the International Conference on Machine Learning (ICML). pp. 19730\u201319742. PMLR (2023)"},{"key":"20_CR25","doi-asserted-by":"crossref","unstructured":"Li, R., Li, S., Kong, L., Yang, X., Liang, J.: SeeGround: See and ground for Zero-Shot Open-Vocabulary 3D visual grounding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2025)","DOI":"10.1109\/CVPR52734.2025.00351"},{"key":"20_CR26","doi-asserted-by":"crossref","unstructured":"Lin, J., et al.: SeqVLM: proposal-guided multi-view sequences reasoning via VLM for zero-shot 3D visual grounding. In: Proceedings of the 33rd ACM International Conference on Multimedia, pp. 3094\u20133103. ACM MM (2025)","DOI":"10.1145\/3746027.3754985"},{"key":"20_CR27","unstructured":"Liu, Y., Liu, W., Gu, X., Rui, Y., He, X., Zhang, Y.: LMagent: a large-scale multimodal agents society for multi-user simulation. arXiv preprint arXiv:2412.09237 (2024)"},{"key":"20_CR28","doi-asserted-by":"crossref","unstructured":"Liu, Y., et al.: Segment any point cloud sequences by distilling vision foundation models. In: Advances in Neural Information Processing Systems (NeurIPS), vol. 36, pp. 37193\u201337229 (2023)","DOI":"10.52202\/075280-1617"},{"key":"20_CR29","unstructured":"Ma, X., et al.: SQA3D: situated question answering in 3D scenes. In: International Conference on Learning Representations (ICLR) (2023)"},{"issue":"10","key":"20_CR30","doi-asserted-by":"publisher","first-page":"8921","DOI":"10.1109\/LRA.2024.3451395","volume":"9","author":"D Maggio","year":"2024","unstructured":"Maggio, D., et al.: Clio: real-time task-driven open-set 3D scene graphs. IEEE Robot. Autom. Lett. 9(10), 8921\u20138928 (2024)","journal-title":"IEEE Robot. Autom. Lett."},{"key":"20_CR31","doi-asserted-by":"crossref","unstructured":"Man, Y., Gui, L.Y., Wang, Y.X.: Situational awareness matters in 3d vision language reasoning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 13678\u201313688 (2024)","DOI":"10.1109\/CVPR52733.2024.01298"},{"key":"20_CR32","doi-asserted-by":"crossref","unstructured":"Mascaro, R., Chli, M.: Scene representations for robotic spatial perception. Annual Review of Control, Robot. Auton. Syst. 8 (2024)","DOI":"10.1146\/annurev-control-040423-030709"},{"key":"20_CR33","unstructured":"Oquab, M., et al.: Dinov2: Learning robust visual features without supervision. arXiv preprint arXiv:2304.07193 (2023)"},{"key":"20_CR34","unstructured":"Qi, Z., Zhang, Z., Fang, Y., Wang, J., Zhao, H.: Gpt4scene: Understand 3D scenes from videos with vision-language models. arXiv preprint arXiv:2501.01428 (2025)"},{"key":"20_CR35","unstructured":"Ramakrishnan, S.K., et al.: Habitat-matterport 3D dataset (HM3D): 1000 large-scale 3d environments for embodied AI. arXiv preprint arXiv:2109.08238 (2021)"},{"key":"20_CR36","doi-asserted-by":"crossref","unstructured":"Rosinol, A., Gupta, A., Abate, M., Shi, J., Carlone, L.: 3D dynamic scene graphs: actionable spatial perception with places, objects, and humans. arXiv preprint arXiv:2002.06289 (2020)","DOI":"10.15607\/RSS.2020.XVI.079"},{"key":"20_CR37","doi-asserted-by":"crossref","unstructured":"Schult, J., Engelmann, F., Hermans, A., Litany, O., Tang, S., Leibe, B.: Mask3D: mask transformer for 3D semantic instance segmentation. In: 2023 IEEE International Conference on Robotics and Automation (ICRA), pp. 8216\u20138223. IEEE (2023)","DOI":"10.1109\/ICRA48891.2023.10160590"},{"key":"20_CR38","doi-asserted-by":"crossref","unstructured":"Shen, Z., Luo, H., Chen, K., Lv, F., Li, T.: Enhancing multi-robot semantic navigation through multimodal chain-of-thought score collaboration. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 39, pp. 14664\u201314672 (2025)","DOI":"10.1609\/aaai.v39i14.33607"},{"key":"20_CR39","unstructured":"Taguchi, S., Deguchi, H., Hamazaki, T., Sakai, H.: SpatialPrompting: keyframe-driven zero-shot spatial reasoning with off-the-shelf multimodal large language models. arXiv preprint arXiv:2505.04911 (2025)"},{"key":"20_CR40","unstructured":"Vera, A., Sanchez, K., Hinojosa, C., Hamid, H.B., Kim, D., Ghanem, B.: Multimodal safety evaluation in generative agent social simulations. arXiv preprint arXiv:2510.07709 (2025)"},{"key":"20_CR41","doi-asserted-by":"crossref","unstructured":"Wang, H., Zhao, Y., Wang, T., Fan, H., Zhang, X., Zhang, Z.: Ross3d: Reconstructive visual instruction tuning with 3d-awareness. arXiv preprint arXiv:2504.01901 (2025)","DOI":"10.1109\/ICCV51701.2025.00866"},{"key":"20_CR42","unstructured":"Wang, P., et\u00a0al.: Qwen2-VL: enhancing vision-language model\u2019s perception of the world at any resolution. arXiv preprint arXiv:2409.12191 (2024)"},{"key":"20_CR43","doi-asserted-by":"crossref","unstructured":"Wang, X., et al.: Reinforced cross-modal matching and self-supervised imitation learning for vision-language navigation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6629\u20136638 (2019)","DOI":"10.1109\/CVPR.2019.00679"},{"key":"20_CR44","doi-asserted-by":"crossref","unstructured":"Wu, D., Liu, F., Hung, Y.H., Duan, Y.: Spatial-MLLM: boosting MLLM capabilities in visual-based spatial intelligence. arXiv preprint arXiv:2505.23747 (2025)","DOI":"10.52202\/085713-0457"},{"key":"20_CR45","doi-asserted-by":"crossref","unstructured":"Wu, S.C., Wald, J., Tateno, K., Navab, N., Tombari, F.: Scenegraphfusion: Incremental 3d scene graph prediction from RGB-D sequences. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 7515\u20137525 (2021)","DOI":"10.1109\/CVPR46437.2021.00743"},{"key":"20_CR46","doi-asserted-by":"crossref","unstructured":"Xia, F., Zamir, A.R., He, Z., Sax, A., Malik, J., Savarese, S.: Gibson ENV: real-world perception for embodied agents. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 9068\u20139079 (2018)","DOI":"10.1109\/CVPR.2018.00945"},{"key":"20_CR47","doi-asserted-by":"crossref","unstructured":"Xie, Q., Liang, Z., Zeng, L.: DSM: Building a diverse semantic map for 3D visual grounding. arXiv preprint arXiv:2504.08307 (2025)","DOI":"10.1109\/LRA.2026.3678129"},{"key":"20_CR48","unstructured":"Xu, R., Huang, Z., Wang, T., Chen, Y., Pang, J., Lin, D.: VLM-Grounder: a VLM agent for zero-shot 3D visual grounding. In: Conference on Robot Learning (CoRL) (2024)"},{"key":"20_CR49","doi-asserted-by":"crossref","unstructured":"Yang, J., et al.: LLM-grounder: open-vocabulary 3D visual grounding with large language model as an agent. In: 2024 IEEE International Conference on Robotics and Automation (ICRA), pp. 7694\u20137701. IEEE (2024)","DOI":"10.1109\/ICRA57147.2024.10610443"},{"key":"20_CR50","doi-asserted-by":"crossref","unstructured":"Yang, J., Yang, S., Gupta, A.W., Han, R., Fei-Fei, L., Xie, S.: Thinking in space: how multimodal large language models see, remember, and recall spaces. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 10632\u201310643 (2025)","DOI":"10.1109\/CVPR52734.2025.00994"},{"key":"20_CR51","doi-asserted-by":"crossref","unstructured":"Yang, Y., Hayat, M., Jin, Z., Zhu, H., Lei, Y.: Zero-shot point cloud segmentation by semantic-visual aware synthesis. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 11586\u201311596 (2023)","DOI":"10.1109\/ICCV51070.2023.01064"},{"key":"20_CR52","unstructured":"Yuan, Q., Li, K., Zhang, J.: Solving zero-shot 3D visual grounding as constraint satisfaction problems. arXiv preprint arXiv:2411.14594 (2024)"},{"key":"20_CR53","unstructured":"Yuan, Z., et\u00a0al.: Mora: enabling generalist video generation via a multi-agent framework. arXiv preprint arXiv:2403.13248 (2024)"},{"key":"20_CR54","doi-asserted-by":"crossref","unstructured":"Yuan, Z., et al.: Empowering large language models with 3D situation awareness. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 19435\u201319445 (2025)","DOI":"10.1109\/CVPR52734.2025.01810"},{"key":"20_CR55","doi-asserted-by":"crossref","unstructured":"Yuan, Z., Ren, J., Feng, C.M., Zhao, H., Cui, S., Li, Z.: Visual programming for zero-shot open-vocabulary 3D visual grounding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 20623\u201320633 (2024)","DOI":"10.1109\/CVPR52733.2024.01949"},{"key":"20_CR56","doi-asserted-by":"publisher","unstructured":"Zhang, S., et al.: Agent3d-zero: an agent for zero-shot 3D understanding. In: Leonardis, A., Ricci, E., Roth, S., Russakovsky, O., Sattler, T., Varol, G. (eds.) ECCV 2024. LNCS, vol. 15077, pp. 186\u2013202. Springer, Cham (2024). https:\/\/doi.org\/10.1007\/978-3-031-72655-2_11","DOI":"10.1007\/978-3-031-72655-2_11"},{"key":"20_CR57","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Luo, H., Lei, Y.: Towards CLIP-driven language-free 3D visual grounding via 2D-3D relational enhancement and consistency. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 13063\u201313072 (2024)","DOI":"10.1109\/CVPR52733.2024.01241"},{"key":"20_CR58","doi-asserted-by":"crossref","unstructured":"Zhao, L., Cai, D., Sheng, L., Xu, D.: 3DVG-transformer: relation modeling for visual grounding on point clouds. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 2928\u20132937 (2021)","DOI":"10.1109\/ICCV48922.2021.00292"},{"key":"20_CR59","unstructured":"Zhao, X., et al.: Fast segment anything. arXiv preprint arXiv:2306.12156 (2023)"},{"key":"20_CR60","doi-asserted-by":"crossref","unstructured":"Zheng, D., Huang, S., Wang, L.: Video-3D LLM: learning position-aware video representation for 3d scene understanding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 8995\u20139006 (2025)","DOI":"10.1109\/CVPR52734.2025.00841"},{"key":"20_CR61","doi-asserted-by":"crossref","unstructured":"Zhi, H., et al.: LsceneLLM: enhancing large 3D scene understanding using adaptive visual preferences. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3761\u20133771 (2025)","DOI":"10.1109\/CVPR52734.2025.00356"},{"key":"20_CR62","doi-asserted-by":"crossref","unstructured":"Zhou, Y., et al.: ReAgent-V: a reward-driven multi-agent framework for video understanding. arXiv preprint arXiv:2506.01300 (2025)","DOI":"10.52202\/085713-5066"},{"key":"20_CR63","doi-asserted-by":"crossref","unstructured":"Zhu, Z., Ma, X., Chen, Y., Deng, Z., Huang, S., Li, Q.: 3D-vista: pre-trained transformer for 3D vision and text alignment. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 2911\u20132921 (2023)","DOI":"10.1109\/ICCV51070.2023.00272"},{"key":"20_CR64","doi-asserted-by":"crossref","unstructured":"Zhu, Z., et\u00a0al.: Move to understand a 3D scene: bridging visual grounding and exploration for efficient and versatile embodied navigation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 8120\u20138132 (2025)","DOI":"10.1109\/ICCV51701.2025.00761"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2026"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-37041-9_20","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T07:30:32Z","timestamp":1788939032000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37041-9_20"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032370402","9783032370419"],"references-count":64,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37041-9_20","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"10 September 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Malm\u00f6","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sweden","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 September 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 September 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}